We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task -- transcribing audio inputs into pseudo subword sequences. This process stands on its own, or can be applied as low-cost second-stage pre-training. We experiment with automatic speech recognition (ASR), spoken named entity recognition, and speech-to-text translation. We set new state-of-the-art results for end-to-end spoken named entity recognition, and show consistent improvements on 20 language pairs for speech-to-text translation, even when competing methods use additional text data for training. Finally, on ASR, our approach enables encoder-decoder methods to benefit from pre-training for all parts of the network, and shows comparable performance to highly optimized recent methods.
@article{arxiv.2205.01086,
title = {Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages},
author = {Felix Wu and Kwangyoun Kim and Shinji Watanabe and Kyu Han and Ryan McDonald and Kilian Q. Weinberger and Yoav Artzi},
journal= {arXiv preprint arXiv:2205.01086},
year = {2022}
}
Comments
Code available at https://github.com/asappresearch/wav2seq